Controlled time series generation for automotive software-in-the-loop testing using GANs
Paper in proceeding, 2020

Testing automotive mechatronic systems partly uses the software-in-the-loop approach, where systematically covering inputs of the system-under-test remains a major challenge. In current practice, there are two major techniques of input stimulation. One approach is to craft input sequences which eases control and feedback of the test process but falls short of exposing the system to realistic scenarios. The other is to replay sequences recorded from field operations which accounts for reality but requires collecting a well-labeled dataset of sufficient capacity for widespread use, which is expensive. This work applies the well-known unsupervised learning framework of Generative Adversarial Networks (GAN) to learn an unlabeled dataset of recorded in-vehicle signals and uses it for generation of synthetic input stimuli. Additionally, a metric-based linear interpolation algorithm is demonstrated, which guarantees that generated stimuli follow a customizable similarity relationship with specified references. This combination of techniques enables controlled generation of a rich range of meaningful and realistic input patterns, improving virtual test coverage and reducing the need for expensive field tests.

generative adversarial net-works

time series generation

latent space arithmetic

software-in-the-loop

Author

Dhasarathy Parthasarathy

Volvo Cars

Karl Bäckström

Chalmers, Computer Science and Engineering (Chalmers), Networks and Systems (Chalmers)

Jens Henriksson

Chalmers, Computer Science and Engineering (Chalmers)

Sólrún Einarsdóttir

Chalmers, Computer Science and Engineering (Chalmers), Functional Programming

Proceedings - 2020 IEEE International Conference on Artificial Intelligence Testing, AITest 2020

39-46 9176782
9781728169842 (ISBN)

2nd IEEE International Conference on Artificial Intelligence Testing, AITest 2020
Oxford, United Kingdom,

Subject Categories

Bioinformatics (Computational Biology)

Embedded Systems

Computer Systems

DOI

10.1109/AITEST49225.2020.00013

More information

Latest update

11/6/2020